Humanize Content logo

Humanize Content

Organization
swan-gtm
humanize-content

Use this skill when marketing or sales copy reads as machine-written and needs to sound like a person wrote it: AI drafts of articles, web pages, case studies, emails, LinkedIn posts, meta descriptions and FAQ answers. Produces a rewrite that keeps the meaning and facts, removes six specific patterns that give AI copy away, and comes with a checker report. Fires on "humanize this", "this sounds like AI", "make it sound human", "remove the AI tells", "tidy the copy", "does this sound like AI", "edit this draft", "check this against our style", "this reads like a slogan stack".

Overview

Publisherswan-gtm
Repositorygtm-skills
Skill namehumanize-content
Stars
216
Forks
103
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by swan-gtm on GitHub. Read the source before you install it.

Installation

Install the Humanize Content AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/swan-gtm/gtm-skills/tree/main/skills/amith-tk/humanize-content
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/amith-tk/humanize-content .claude/skills/humanize-content
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Humanize Content in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Humanize Content on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Humanize Content is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use when a draft is correct but sounds produced rather than written. Produces a rewrite in plain, connected prose with claims first, evidence attached and a person doing the acting, plus a short list of what changed and what still needs a source.

Load first: the draft, where it will appear (page, email, post, article) and who reads it. Ask whether a brand voice guide or house style exists and follow it where it conflicts with the defaults in references/house-style-options.md. Confirm the few switches that vary by company: English variant, em dashes, banned vocabulary, and whether byline or headline wording is already agreed. The purpose is clarity and voice. It is not to defeat AI detectors, and it never changes who the author is.

The play

  1. Diagnose. Run scripts/lint_style.py on the draft when code execution is available (references/using-the-checker.md). Otherwise test the draft by hand against the six patterns below. Also read for sentences with no verb, which the checker only partly catches.
  2. Rewrite pattern by pattern. Give every sentence a subject and a finite verb, keep every fact and number, and use the fixes in references/retired-patterns.md. Study references/rewrite-bank.md for before-and-after pairs.
  3. Re-check and read aloud. Rerun the checker until no RULE hits remain, decide each CHECK hit, then read the draft once as speech. If it sounds like a stack of statements, join them into continuous prose.
  4. Report. List the patterns removed, the sentences that changed meaning even slightly, and every figure that has no unit, source or date. Ask for those instead of inventing them.

For voice, sentence length and structure, read references/voice-and-structure.md.

The six patterns to retire

PatternLooks likeFix
1. Fragment with a tag"Four layers, built in order."Give it a subject and a verb: "The stack has four layers, and each rests on the one beneath."
2. The "so" splice"Pages that explain the category, so the buyer reads yours first."Make the effect the main verb, put the condition first, or use "because".
3. "Worth" and other editorial nudges"worth noting", "it is important to note", "keep in mind"State the thing and, if needed, the reason it matters.
4. "Long before" and "long after""long before anyone books a call"Give the interval or name the event: "months before".
5. The "none of it" closer"None of that makes the decision less human."State the positive fact, or use a precise negative.
6. The sentence that announces its point"The part that compounds is deciding what to say."Let the actor do the thing: "Content compounds when a company decides what to say."

Related contrast shapes ("not just X but Y", "X, not Y", "is not X, it is Y", parallel-pair headings such as "Two teams, one goal") are on by default and can be switched off.

What good looks like

  • Meaning survives. Every fact, name, number and qualification in the original is still there, unless the user agreed to cut it.
  • Claim first. The most important sentence leads the page, the section and the paragraph.
  • Sentences hold 15 to 30 words, with a ceiling near 40, and no more than two in a row under eight words.
  • Connectors vary ("because", "while", "although", "when", "but", "yet"), and condition-first phrasing often removes the connector entirely.
  • People are the subject. Buyers, teams and companies act; abstractions rarely do.
  • Numbers carry a unit, a named source and a year. Missing ones are flagged, never invented.
  • Confidence is calibrated: sourced facts stated flatly, forecasts hedged with "could", "may" or "usually".
  • The mediocre version swaps words for synonyms and leaves the same skeleton, or swaps one tell for another (every "so" becomes ", which"), or flattens a distinctive voice into beige.
  • Done when the checker reports no RULE hits and the draft reads naturally aloud.

Rules

  • MUST preserve facts, names and figures, and flag any change in meaning.
  • MUST ask for a source or unit instead of making one up.
  • MUST leave intentional examples alone: quoted "what not to write" demonstrations, legal wording that needs exact phrasing, and literal money values such as "worth $5 million".
  • MUST ask before changing headlines, slogans or bylines the owner has already approved.
  • NEVER invent statistics, quotes, client names or sources.
  • NEVER present a rewrite as undetectable by AI-detection tools.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Humanize Content AI skill do?

Use this skill when marketing or sales copy reads as machine-written and needs to sound like a person wrote it: AI drafts of articles, web pages, case studies, emails, LinkedIn posts, meta descriptions and FAQ answers. Produces a rewrite that keeps the meaning and facts, removes six specific patterns that give AI copy away, and comes with a checker report. Fires on "humanize this", "this sounds like AI", "make it sound human", "remove the AI tells", "tidy the copy", "does this sound like AI", "edit this draft", "check this against our style", "this reads like a slogan stack".

Why use Humanize Content on TypingMind?

Because you install it once and use it with any model. Humanize Content is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Humanize Content in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan-gtm/gtm-skills/tree/main/skills/amith-tk/humanize-content. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Humanize Content?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Humanize Content?

As many as you like. As long as a model supports skills, you can use Humanize Content with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Humanize Content AI skill free?

Yes. It is published on GitHub by swan-gtm under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇